How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses

no code implementations • 18 May 2023 • Joana C. Costa, Tiago Roxo, Hugo Proença, Pedro R. M. Inácio

Deep Learning is currently used to perform multiple tasks, such as object recognition, face recognition, and natural language processing.

Face Recognition Malware Detection +1

WASD: A Wilder Active Speaker Detection Dataset

1 code implementation • 9 Mar 2023 • Tiago Roxo, Joana C. Costa, Pedro R. M. Inácio, Hugo Proença

The results show that: 1) AVA trained models maintain a state-of-the-art performance in WASD Easy group, while underperforming in the Hard one, showing the 2) similarity between AVA and Easy data; and 3) training in WASD does not improve models performance to AVA levels, particularly for audio impairment and surveillance settings.